A machine learning approach identifies modulators of heart failure hospitalization prevention among patients with type 2 diabetes: A revisit to the ACCORD trial

Abstract

BackgroundTo examine patient characteristics that may modulate the heterogeneous treatment effect of intensive systolic blood pressure control (SBP) and intensive glycemic control on incident heart failure (HF) risk in people with type 2 diabetes. MethodsWe analyzed 10,251 participants from the ACCORD glucose trial, and 4733 from the SBP sub-trial separately. We applied a robust machine-learning (ML) algorithm, namely the causal forest/causal tree analysis, to each trial to identify participants' characteristics that modulate the effectiveness of each trial intervention. ResultsDiastolic blood pressure (DBP) was found to interact with intensive glycemic control and impact outcomes. An increased HF risk associated with intensive glycemic control (absolute risk change (ARC): 2.28 %, 95 % confidence interval (CI): 0.69 % to 3.90 %; relative risk (RR):1.57, 95 % CI: 1.15 to 2.20; P < 0.05) was observed in individuals with baseline DBP at the lowest tertile (45–69 mmHg), while no changes in HF risk associated with intensive glycemic control were observed in individuals with baseline DBP at the middle (70–79 mmHg) and the highest tertiles (80–100 mmHg). Liver function was identified as a modulator of intensive BP control, and baseline Alanine transaminase (ALT) level was a sensitive marker for the modulating effect. Only individuals with baseline ALT at the lowest tertile (8–19 mg/dl) benefited from the intensive BP control for HF prevention (ARC: −1.95 %, 95 % CI: −4.06 % to 0.11 %; RR:0.62. 95 % CI: 0.27 to 0.94; P < 0.05). ConclusionsOur study is the first to observe and quantify the potential synergistic harmful effect when low DBP was combined with an intensive blood glucose intervention. Recognizing these may help clinicians develop a more precise approach to such treatments, thus increasing the efficiency and outcomes of diabetes treatments.